Triple
T35863885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Taylor |
E1037028
|
entity |
| Predicate | politicalPartyOfHusband |
P113365
|
FINISHED |
| Object | Whig Party |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Whig Party | Statement: [Margaret Taylor, politicalPartyOfHusband, Whig Party]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalPartyOfHusband Context triple: [Margaret Taylor, politicalPartyOfHusband, Whig Party]
-
A.
titleHolderSpousePoliticalParty
chosen
Indicates that the predicate links a title holder’s spouse to the political party with which that spouse is affiliated.
-
B.
partyOfCandidate
Indicates the political party with which a given candidate is affiliated.
-
C.
partnerPoliticalAffiliation
Indicates that one entity has a political affiliation that is associated with, or shared by, its partner entity.
-
D.
spousePoliticalAlignment
Indicates that two individuals are spouses and specifies the political alignment or affiliation associated with that spousal relationship.
-
E.
subjectPoliticalParty
Indicates the political party with which the subject is formally affiliated or identified.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76e1d279c8190843e5b64a0a12c3f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fed357b2b4819084c709056a54461f |
completed | May 9, 2026, 6:25 a.m. |
| PD | Predicate disambiguation | batch_69fed103d9cc81909b11619745110c61 |
completed | May 9, 2026, 6:15 a.m. |
Created at: May 3, 2026, 4:06 p.m.